No article text was recorded for this version.
ergodicity assumption
Version 2 of 2254 papers300 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Provable Policy Gradient Methods for Average-Reward Markov Potential Games
- Blog: Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path
- Blog: Posterior Sampling for Reinforcement Learning Without Episodes
- Blog: Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
- Blog: Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
- Blog: Provably Efficient Adaptive Approximate Policy Iteration
- Blog: Average-Reward Reinforcement Learning with Trust Region Methods
- Blog: Convergence Rates of Posterior Distributions in Markov Decision Process
- Blog: Inverse Reinforcement Learning with the Average Reward Criterion
- Blog: Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
- Blog: Active Model Estimation in Markov Decision Processes
- Blog: Towards Tight Bounds on the Sample Complexity of Average-reward MDPs
- Blog: Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
- Blog: Inverse Reinforcement Learning with the Average Reward Criterion
- Blog: Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes
- Blog: Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
- Blog: Reinforcement Learning for Cost-Aware Markov Decision Processes
- Blog: Markov Decision Processes with Long-Term Average Constraints
- Blog: Algorithm for Constrained Markov Decision Process with Linear Convergence
- Blog: Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games
- Blog: Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
- Blog: Active Model Estimation in Markov Decision Processes
- Blog: Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
- Blog: Exploration in Structured Reinforcement Learning
- Blog: Sample Complexity Characterization for Linear Contextual MDPs
- Blog: Optimal Sample Complexity for Average Reward Markov Decision Processes
- Blog: Active Exploration in Markov Decision Processes
- Blog: Learning to Coordinate Efficiently: A Model-based Approach
- Blog: Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs
- Blog: Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning
- Blog: Asymptotically optimal regret in communicating Markov decision processes
- Blog: Exploration-Exploitation Trade-off in Reinforcement Learning on Online Markov Decision Processes with Global Concave Rewards
- Blog: Improved Regret Bound and Experience Replay in Regularized Policy Iteration
- Blog: Spectral Learning for Infinite-Horizon Average-Reward POMDPs
- Blog: Thompson Sampling for Learning Parameterized MDPs
- Blog: Reinforcement Learning of Contextual MDPs using Spectral Methods
- Blog: Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process
- Blog: Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
- Blog: IMED-RL: Regret optimal learning of ergodic Markov decision processes
- Blog: Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs
- Blog: Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs
- Blog: Average-Reward Reinforcement Learning with Trust Region Methods
- Blog: Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning
- Blog: Autonomous Reinforcement Learning: Formalism and Benchmarking
- Blog: Concave Utility Reinforcement Learning with Zero-Constraint Violations
- Blog: Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes
- Blog: Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives
- Blog: Two Timescale Stochastic Approximation with Controlled Markov noise
- Blog: A Provably Efficient Sample Collection Strategy for Reinforcement Learning
- Blog: Markov Persuasion Processes with Endogenous Agent Beliefs
- Blog: Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
- Blog: Corrected: On Confident Policy Evaluation for Factored Markov Decision Processes with Node Dropouts
- Blog: Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
- Blog: Robust Average-Reward Reinforcement Learning
- Blog: Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
- Blog: Provable Policy Gradient Methods for Average-Reward Markov Potential Games
- Blog: On Q-learning Convergence for Non-Markov Decision Processes
- Blog: Convergence of Optimistic and Incremental Q-Learning
- Blog: A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret
- Blog: Reinforcement Learning with Soft State Aggregation
Showing 60 of 254 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_ergodicity_assumption_f03c3d0f,
title = {ergodicity assumption},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ergodicity-assumption/rdr_f03c3d0f52bc4e109af8815b088467ec},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_ergodicity_assumption_f03c3d0f_v2,
title = {ergodicity assumption},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ergodicity-assumption/rdr_f03c3d0f52bc4e109af8815b088467ec/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}